Personal Robotics Laboratory Department of Electrical and Electronic Engineering Imperial College London, South Kensington Campus London SW7 2AZ, UK

Transcription

1 Hyung Jin Chang Contact Information Personal Robotics Laboratory Department of Electrical and Electronic Engineering Imperial College London, South Kensington Campus London SW7 2AZ, UK Mobile: +44(0) Fax: +44(0) Citizenship Research Interests Education Republic of Korea Machine learning and its application to computer vision and robot vision; visual object tracking, adaptive background subtraction, action recognition and articulated structure reconstruction from visual input sequences. Seoul National University, Seoul, Korea Ph.D., School of Electrical Engineering and Computer Science, February 2013 Thesis Title: Attentional Sampling for Efficient Visual Computing Adviser: Prof. Jin Young Choi Area of Study: Machine Learning and its application to computer vision area B.S., School of Electrical Engineering and Computer Science, February 2006 Thesis Title: Robot Behavior Learning Model based on Motivation and Hierarchical Emotion Bronze Medal in Electrical Fair of SNU, 2004 Professional Journal Publications Research Associate, Personal Robotics Lab., Imperial College London, 2014-Present. Research Associate, Imperial Computer Vision and Learning Lab., Imperial College London, Researcher, Automation and Systems Research Institute, Seoul National University, Teaching assistant, EECS, Seoul National University, R&D Intern,Hynix Semiconductor Co. Ltd., Youngkyoon Jang, Seung-Tak Noh, Hyung Jin Chang, Tae-Kyun Kim, and Woontack Woo, 3D Finger CAPE: Clicking Action and Position Estimation under Self- Occlusions in Egocentric Viewpoint, IEEE Transactions on Visualization and Computer Graphics (TVCG), vol.21, no.4, Kyuhwa Lee, Dimitri Ognibene, Hyung Jin Chang, Tae-Kyun Kim, and Yiannis Demiris, STARE: Spatio-Temporal Attention RElocation for Multiple Structured Activities Detection, IEEE Transactions on Image Processing (TIP), under review. Hyung Jin Chang, Guillermo Garcia-Hernando, Danhang Tang, and Tae-Kyun Kim, Spatio-Temporal Hough Forest for Efficient Detection-Localisation-Recognition of Fingerwriting in Egocentric Camera, Computer Vision and Image Understanding (CVIU), under review. 1 of 6

2 Jungchan Cho, Minsik Lee, Hyung Jin Chang, and Songhwai Oh, Robust Action Recognition using Local Motion and Group Sparsity, Pattern Recognition, Vol.47, Issue 5, May Hyung Jin Chang, Dong Sung Song, Pyo Jae Kim, and Jin Young Choi, Spatiotemporal Pattern Modeling for Fault Detection and Classification in Semiconductor Manufacturing, IEEE Transaction on Semiconductor Manufacturing, Vol.25, No 1, February JinMin Choi, Hyung Jin Chang, Yung Jun Yoo, and Jin Young Choi, Robust Moving Object Detection against Fast Illumination Change, Computer Vision and Image Understanding (CVIU), pages , Vol.116, Issue 2, February Hawook Jeong, Hyung Jin Chang, and Jin Young Choi, Unsupervised Motion Learning for Abnormal Behavior Detection in Visual Surveillance, The Magazine of the IEEK, Vol.48, Issue 5, pages 45-51, September Hyung Jin Chang, Pyo Jae Kim, Dong Sung Song, and Jin Young Choi, Optical Image Stabilizing System using Multirate Fuzzy PID Controller for Mobile Device Camera, IEEE Transactions on Consumer Electronics, Vol.55, No.2, May Conference Publications Hyung Jin Chang, Yiannis Demiris, Unsupervised Learning of Complex Articulated Kinematic Structures combining Motion and Skeleton Information, IEEE Proc. Computer Vision and Pattern Recognition (CVPR), June, Youngkyoon Jang, Seung-Tak Noh, Hyung Jin Chang, Tae-Kyun Kim, Woontack Woo, 3D Finger CAPE: Clicking Action and Position Estimation under Self-Occlusions in Egocentric Viewpoint, IEEE Virtual Reality (VR), March, [full paper, accept rate=13.8%] Danhang Tang, Hyung Jin Chang, Alykhan Tejani, Tae-Kyun Kim, Latent Regression Forest: Structural Estimation of 3D Articulated Hand Posture, IEEE Proc. Computer Vision and Pattern Recognition (CVPR), June, Oral Kwang Yi, Hawook Jeong, Byeongho Heo, Hyung Jin Chang, Jin Young Choi, Initialization- Insensitive Visual Tracking Through Voting with Salient Local Features, International Conference on Computer Vision (ICCV), December, Hyung Jin Chang, Jiyun Kim, Jungchan Cho, Songhwai Oh, Kwang Moo Yi, and Jin Young Choi, Action Chart: A Representation for Efficient Recognition of Complex Activities, British Machine Vision Conference (BMVC), September, Tushar Sandhan, Hyung Jin Chang, and Jin Young Choi, Abstracted Radon Profiles for Fingerprint Recognition, International Conference on Image Processing (ICIP), September Kwang Moo Yi, Kimin Yun, Soo Wan Kim, Hyung Jin Chang, Hawook Jeoung, and Jin Young Choi, Detection of Moving Objects with Non-Stationary Cameras in 5.8ms: Bringing Motion Detection to your Mobile Device, CVPR Workshops on Mobile Vision June [Best paper awarded] Moonsub Byeon, Hyung Jin Chang, and Jin Young Choi, Hierarchical Feature Grouping for Multiple Object Segmentation and Tracking, IVCNZ, Nov , Hyung Jin Chang, Hawook Jeong, and Jin Young Choi, Active Attentional Sampling for Speed-up of Background Subtraction, IEEE Proc. Computer Vision and Pattern Recognition (CVPR), June 16-21, of 6

3 Hyung Jin Chang, Kwang Moo Yi, Shimin Yin, Soo Wan Kim, Young Min Baek, Ho Seok Ahn, and Jin Young Choi, PIL-EYE: Integrated System for Sustainable Development of Intelligent Visual Surveillance Algorithms, IEEE Digital Image Computing: Techniques and Applications (DICTA) 2011, December 6-8, Oral Hyung Jin Chang, Myoung Soo Park, Hawook Jeong, and Jin Young Choi, Tracking Failure Detection by Imitating Human Visual Perception, IEEE International Conference on Image Processing (ICIP), September 11-14, Hawook Jeong, Hyung Jin Chang, and Jin Young Choi, Modeling of Moving Object Trajectory by Spatio-temporal Learning for Abnormal Behavior Detection, IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Aug 30 - Sep 2, D. Pokrajac, N. Reljin, N. Pejcic, T. Vance, S. McDaniel, A. Lazarevic, H. J. Chang, J. Y. Choi, and R. Miezianko, Detection of Suspious Activity Using Incremental Outlier Detection Algorithms, SPIE Signal and Data Processing on Small Targets 2009 conference, August, Pyo Jae Kim, Hyung Jin Chang, and Jin Young Choi, Fast Incremental Learning for One-class Support Vector Classifier usingsample Margin Information, 19th Internationa Conference on Pattern Recognition (ICPR), Tampa, Florida, Dec Oral Pyo Jae Kim, Hyung Jin Chang, Dong Sung Song, and Jin Young Choi, Fast Support Vector Data Description Using K-Means Clustering, Lecture Notes in Computer Science (LNCS), Vol. 4493, Proceeding of the 4th International Symposium on Neural Networks: Advances in Neural Networks, pp , June Hyung Jin Chang, Pyo Jae Kim, Jung Hwan Choi, and Jin Young Choi, Support Vector Data Description Using Clustering Method, International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2007), Vol. 3, pp , July Oral Ho Seok Ahn, Pyo Jae Kim, Jeong Hwan Choi, Bin Mansoor, S., Woo-Sung Kang, Seok Min Yoon, Jin Hee Na, Young Min Baek, Hyung Jin Chang, Dong Sung Song, Jin Young Choi, Hyeong-Seok Ko, Emotional head robot with behavior decision model and face recognition, Control, Automation and Systems, ICCAS Hyung Jin Chang, Pyo Jae Kim, Jeong Hwan Choi, and Jin Young Choi, Support Vector Data Description using Mean Shift Clustering, Information and Control Symposium (ICS), April, Oral Pyo Jae Kim, Hyung Jin Chang, Dong Sung Song, and Jin Young Choi, KMSVDD: Support Vector Data Description using K-means Clustering, Information and Control Symposium (ICS), April, Best paper awarded. Patents EU Patent EP Hand-Shake Correction Method and Apparatus of Camera Module for Use in Mobile Device. EU Patent EP Apparatus and Method for Proportional-Integral-Derivative Control. US Patent US Hand-Shake Correction Method and Apparatus of Camera Module for Use in Mobile Device. US Patent US Apparatus and Method for Proportional-Integral-Derivative Control. KOR Patent Method and apparatus for optical image stabilizer on mobile camera module. (March, 2008) (PCT: EU, China) 3 of 6

4 KOR Patent Proportional-integrate-derivative control apparatus and method. (October, 2008) (PCT: EU, China) KOR Patent Fault detection method using sequential one class classifier chain. (September, 2010) KOR Patent applied Image processing apparatus capable of reducing calculation rates which are necessary to detect an object. (July, 2010) KOR Patent Method of Providing Fast Detection of Moving Objects from Non-stationary Camera Video by Dual-mode SGM, and Computer-readable Recording Medium for the same. US Patent applied Estimator Training Method and Pose Estimating Method using Depth Image. Awards and Honours CVPR Workshop on Mobile Vision Best Paper Award 2013 CVPR2012 Doctoral Consortium 2012 SNU BK21 Information Technology Excellent research Award Best Paper of ICS2011, 2011 Best Paper of ICS2006, 2006 Bronze Medal in SNU Electrical Fair Outstanding Student Scholarship Department of Electrical Engineering Scholarship International School Teaching Experience Position of Responsibilities Research Project Experience International Computer Vision Summer School (ICVSS) Registration, Recognition and Reconstruction in Images and Video, July 2011, Sampieri-Sicily, Italy Seoul National University, Seoul, Korea Teaching Assistant Linear System Theory (graduate course) Mar 2010 to Jul 2010 Convex Optimization (graduate course) Sep 2009 to Dec 2009 Statistical Learning Theory (graduate course) Mar 2009 to Jul 2009 Developed supplementary course material Strategy for Management of Technology (graduate) Sep 2007 to Dec 2008 Signal and System (undergraduate course) Mar 2007 to Jul 2007 Circuits and Electronics Laboratory (undergraduate) Sep 2006 to Dec 2006 Lab Leader (from Nov to Oct. 2010) Was in charge of project scheduling, job distributing, and coordinating feedback of research members. What You Say Is What You Did (WYSIWYD) June 2014 to Present This work was supported in part by the EU FP7 project WYSIWYD under Grant This project will create a new transparency in human robot interaction (HRI) by allowing robots to both understand their own actions and those of humans, and to interpret and communicate these in human compatible intentional terms expressed as a language-like communication channel. My contribution to this project is learning body schema through visual input data. 4 of 6

5 Hand Posture Recognition in Arbitrary View from Single RGBD Frame June 2013 to May 2014 Sponsored by Samsung Advanced Institute of Technology. The goal of the project is developing a comprehensive method for hand posture recognition in arbitrary view from single frame RGBD data. We consider to estimate hand postures from individual depth frames provided by either popular sensors such as Kinect, or higher resolution ones. Mobile Object Recognition for Information Sharing Service May 2011 to Nov 2011 Sponsored by Samsung Electronics Co., Ltd. The goal of the project is developing an object information sharing system between mobile platform users and a server by visual object recognition. My contribution to this project is as follows: A project leader. Development of the object recognition server system The server system communicates with mobile clients. Object recognition is performed about the client s query image and information of the object is sent back to the client. Intelligent Visual Surveillance System Mar 2008 to Oct 2010 Sponsored by Samsung Techwin Co., Ltd. The goal of the project is developing visual analysis algorithms, such as background subtraction, object tracking and behavior understanding, and integrated system. My contribution to this project is as follows: Development of a speed boosting algorithm for background subtraction. The algorithm speeded up computational time by four times without performance degradation. I wrote one conference paper and one patent about this algorithm. Development of an intelligent visual surveillance platform named as PIL-EYE system. The system architecture is extensible and flexible. It improves algorithm developing time and algorithm performance. The architecture is used for Samsung Techwin s commercial system now. A project leader. I was in charge of a project scheduling, job distributing, and coordinating feedback of research members and Samsung Techwin company. Semiconductor Manufacturing Fault Detection System Aug 2007 to Feb 2008 Sponsored by the Small and Medium Business Administration and Nanotek Company. My contribution to this project is as follows: Design of an online fault detection method for manufacturing process. The method improves the precision of fault detection and easily detects the process start/end points. I wrote one journal paper and one patent. The system is selling as a commercial product now. Optical Image Stabilizer (OIS) for Mobile Device Camera Jan 2006 to Aug 2006 Funded by Samsung Electronics Co., Ltd. My contribution to this project is as follows: Design of a motor controller and its system for optical image stabilizing of mobile device, such as cell phone and camcorder. The developed OIS system showed the most accurate and robust image stabilization performance compared to other commercial cameras. I wrote one journal paper and two patents. 5 of 6

6 R&D Internship at Hynix Semiconductor Co. Ltd. Jul 2003 to Sep 2003 Market surveying and benchmarking of global Bluetooth market growth and forecast. Peer-review Activities References Journal IEEE TPAMI, IEEE TCSVT, IEEE TIE, IEEE TCST Conference IEEE ICCSIT 2011, IVCNZ 2012, ICPR 2012, IROS 2015 Prof. Jin Young Choi Professor in School of Electrical Engineering and Computer Science, Seoul National University Dr. Yiannis Demiris Reader(Associate Professor) in Department of Electrical and Electronic Engineering of Imperial College London Dr. Tae-Kyun Kim Lecturer(Assistant Professor) in Department of Electrical and Electronic Engineering of Imperial College London Prof. Songhwai Oh Assistant Professor in School of Electrical Engineering and Computer Science, Seoul National University Prof. Jongwoo Lim Assistant Professor in Division of Computer Science & Engineering, Hanyang University 6 of 6